大型语言模型在医疗对话问答中需要整体性思考
Large Language Models Need Holistically Thought in Medical Conversational QA
AI总结：
针对医疗对话问答中LLMs推理不足的问题，提出整体性思考（HoT）方法，引导模型进行扩散与聚焦思考，在英中三个数据集上超越SOTA，生成更正确、专业、周到的回答。
摘要：
医疗对话问答（CQA）系统旨在提供一系列专业医疗服务，以提高医疗保健的效率。尽管大型语言模型（LLMs）在数学、逻辑和常识问答等各个领域的复杂推理任务中取得了成功，但面对医疗领域日益增加的复杂性和专业性，它们仍需改进。这是因为医疗CQA任务不仅需要强大的医疗推理能力，还需要广泛而深入思考的能力。在本文中，为了解决这些需要在多方面进行考虑和理解的医疗CQA任务中的挑战，我们提出了整体性思考（HoT）方法，该方法旨在引导LLMs进行扩散性和聚焦性思考，以生成高质量的医疗回答。所提出的HoT方法已通过自动化和人工评估在三个包含英语和中文的不同医疗CQA数据集上进行了评估。大量实验结果表明，与几种最先进（SOTA）方法相比，我们的方法能够产生更正确、更专业、更周到的回答，证明了其有效性。我们的代码位于https://github.com/WENGSYX/HoT。
英文摘要：
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care. Despite the success of large language models (LLMs) in complex reasoning tasks in various fields, such as mathematics, logic, and commonsense QA, they still need to improve with the increased complexity and specialization of the medical field. This is because medical CQA tasks require not only strong medical reasoning, but also the ability to think broadly and deeply. In this paper, to address these challenges in medical CQA tasks that need to be considered and understood in many aspects, we propose the Holistically Thought (HoT) method, which is designed to guide the LLMs to perform the diffused and focused thinking for generating high-quality medical responses. The proposed HoT method has been evaluated through automated and manual assessments in three different medical CQA datasets containing the English and Chinese languages. The extensive experimental results show that our method can produce more correctness, professional, and considerate answers than several state-of-the-art (SOTA) methods, manifesting its effectiveness. Our code in https://github.com/WENGSYX/HoT.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
